© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 92684
    Prev
    Next
    INDEX
    Explanations

    themes related to book covers and their visual appeal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assen
    -0.09
    ennen
    -0.07
    .throw
    -0.06
    idor
    -0.06
    ysize
    -0.06
    zimmer
    -0.06
    ipers
    -0.06
    astle
    -0.06
    åij¨å¹´
    -0.06
     Ones
    -0.06
    POSITIVE LOGITS
    olecule
    0.07
     جذ
    0.06
     appet
    0.06
     spine
    0.06
    aginator
    0.06
     magnet
    0.06
    pell
    0.06
     teaser
    0.06
     bait
    0.06
    :title
    0.06
    Activations Density 0.018%

    No Known Activations